Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1038. Min Act: -0.0001

Data Index: 273471 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0977. Min Act: -0.0001

Data Index: 183989 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1637732 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0859. Min Act: -0.0001

Data Index: 531133 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1613632 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0751. Min Act: -0.0001

Data Index: 271985 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0690. Min Act: -0.0001

Data Index: 645990 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0859. Min Act: -0.0001

Data Index: 592554 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0843. Min Act: -0.0001

Data Index: 915721 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0777. Min Act: -0.0001

Data Index: 311959 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0820. Min Act: -0.0001

Data Index: 313006 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0001

Data Index: 362557 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1205694 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0746. Min Act: -0.0001

Data Index: 770466 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0786. Min Act: -0.0001

Data Index: 3080 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1228275 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0721. Min Act: -0.0001

Data Index: 12295 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0698. Min Act: -0.0001

Data Index: 244401 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0699. Min Act: -0.0001

Data Index: 62722 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0674. Min Act: -0.0001

Data Index: 752350 (C4 (Web Text))

Max Activating Token Index: 856